INDEX

Explanations

key phrases indicating actions, relationships, or characteristics relevant to significant societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÐµÑĢÐµÐ¶

-0.15

peq

-0.15

wz

-0.15

ingham

-0.15

ocol

-0.14

_unused

-0.14

uces

-0.14

htable

-0.14

rades

-0.14

endi

-0.14

POSITIVE LOGITS

 something

0.32

something

0.31

Something

0.27

 Something

0.26

omething

0.20

 nÄĽco

0.18

 iets

0.18

 etwas

0.17

ä½ķãģĭ

0.17

 somehow

0.16

Activations Density 0.005%

key phrases indicating actions, relationships, or characteristics relevant to significant societal issues

No Comments

No Known Activations