INDEX

Explanations

proper nouns and specific identifiers within a context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ocab

-0.16

\Base

-0.15

essen

-0.15

Terminate

-0.14

æļ®

-0.14

 Transcript

-0.14

 bulk

-0.14

prog

-0.14

nw

-0.13

brains

-0.13

POSITIVE LOGITS

lesi

0.16

bum

0.15

Exact

0.15

PostBack

0.14

utz

0.14

 Sheldon

0.14

pbs

0.14

mÃ®

0.14

0.13

Activations Density 0.004%

proper nouns and specific identifiers within a context

No Comments

No Known Activations