INDEX

Explanations

sections of code or comments in programming-related text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

aga

-0.16

ONGL

-0.15

Ð»Ð¸Ð²Ð°

-0.15

 sene

-0.15

zych

-0.15

çª

-0.14

herent

-0.14

 responder

-0.13

.hs

-0.13

elt

-0.13

POSITIVE LOGITS

ÌĨ

0.15

buat

0.14

à¤¯à¤¨

0.13

 Canary

0.13

cid

0.13

/svg

0.13

ocrates

0.13

Ã©ny

0.13

tti

0.13

.dc

0.13

Activations Density 0.010%

sections of code or comments in programming-related text

No Comments

No Known Activations