INDEX

Explanations

code-related keywords and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ogle

-0.15

inder

-0.15

oux

-0.15

GGLE

-0.13

bbing

-0.13

ritel

-0.13

cq

-0.13

 Shaw

-0.13

enan

-0.13

ULER

-0.13

POSITIVE LOGITS

ValuePair

0.16

 Pand

0.15

 Devin

0.15

ismatch

0.15

Ã¼stÃ¼

0.14

 Robbins

0.14

kne

0.14

 Withdraw

0.13

 Perf

0.13

 withdrawals

0.13

Activations Density 0.134%

code-related keywords and syntax elements

No Comments

No Known Activations