INDEX

Explanations

references to eyewitness accounts and statements related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

å®ħ

-0.15

eel

-0.15

iola

-0.14

ocale

-0.14

eba

-0.14

Ø¯Ø¯

-0.14

 Ð¼Ð¸Ð½Ñĥ

-0.14

 mystery

-0.14

oom

-0.13

olian

-0.13

POSITIVE LOGITS

çķ¥

0.15

steder

0.15

erton

0.15

frag

0.14

kker

0.14

reno

0.14

aky

0.14

Activations Density 0.160%

references to eyewitness accounts and statements related to events

No Comments

No Known Activations