INDEX

Explanations

console log statements in code snippets

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/stdc

-0.16

ersh

-0.15

Ľ°

-0.15

ikan

-0.15

DFS

-0.15

foy

-0.15

Ð½Ð¸Ñĩ

-0.14

reau

-0.14

POSITIVE LOGITS

EU

0.14

Ø§Ø¦ÙĤ

0.14

 conting

0.14

ph

0.14

 Prec

0.14

 Burk

0.14

·»

0.14

ãĥ¼ãĥĬ

0.14

 sÃ³c

0.13

ev

0.13

Activations Density 0.014%

console log statements in code snippets

No Comments

No Known Activations