INDEX

Explanations

instances of the word "given" and other terms related to parameters or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 alarm

-0.16

omal

-0.16

 Pres

-0.15

ued

-0.15

 pres

-0.14

alarm

-0.14

Bes

-0.14

Ze

-0.14

PCP

-0.14

and

-0.14

POSITIVE LOGITS

onian

0.16

Ð½Ð¾Ðº

0.15

 taraf

0.15

rokes

0.14

dorf

0.14

axy

0.14

ULA

0.14

ayÄ±p

0.14

ocol

0.14

Activations Density 0.011%

instances of the word "given" and other terms related to parameters or specifications

No Comments

No Known Activations