INDEX

Explanations

terms related to inclusion and the concept of being part of a group or list

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ãģĬãĤĬ

-0.21

uel

-0.17

est

-0.15

ickle

-0.15

kup

-0.15

friend

-0.14

yt

-0.14

POSITIVE LOGITS

/ex

0.35

omanip

0.17

leston

0.16

edere

0.16

ary

0.16

afx

0.16

graphics

0.15

ief

0.15

ARY

0.15

Ã©ment

0.15

Activations Density 0.061%

terms related to inclusion and the concept of being part of a group or list

No Comments

No Known Activations