INDEX

Explanations

programming-related keywords and method declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ADOR

-0.19

ador

-0.16

rending

-0.16

/gcc

-0.16

 Mein

-0.16

-0.14

WXYZ

-0.14

izard

-0.14

ibold

-0.14

esl

-0.14

POSITIVE LOGITS

anya

0.16

 reciprocal

0.16

okrat

0.15

uv

0.15

fu

0.14

Ð¾Ð²Ð¾

0.14

oux

0.14

con

0.14

clud

0.14

ree

0.14

Activations Density 0.005%

programming-related keywords and method declarations

No Comments

No Known Activations