INDEX

Explanations

terms related to biological and medicinal research, particularly focusing on healing and therapeutic effects of plants and compounds

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ukt

-0.15

zyst

-0.15

å¦¹

-0.14

elik

-0.14

ULATOR

-0.14

 Ekim

-0.14

lasses

-0.14

zcze

-0.14

pillar

-0.14

fos

-0.14

POSITIVE LOGITS

 action

0.18

mos

0.16

 actions

0.16

-properties

0.15

 against

0.15

action

0.15

actions

0.15

rop

0.15

uss

0.14

 Clip

0.14

Activations Density 0.108%

terms related to biological and medicinal research, particularly focusing on healing and therapeutic effects of plants and compounds

No Comments

No Known Activations