INDEX

Explanations

commas and various types of names or identifiers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pond

-0.15

asley

-0.14

lap

-0.14

Ð¾Ð³Ð¾Ð´

-0.14

 Lane

-0.14

_terms

-0.13

lo

-0.13

Dag

-0.13

ernes

-0.13

Î±Ïĥ

-0.13

POSITIVE LOGITS

/TT

0.15

idos

0.15

uhe

0.15

ologi

0.14

osten

0.14

ervas

0.14

Â£Â£

0.14

nel

0.13

alnÄ±z

0.13

eriod

0.13

Activations Density 0.016%

commas and various types of names or identifiers

No Comments

No Known Activations