INDEX

Explanations

references to personal involvement or individual experiences in various contexts

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

avn

-0.16

isure

-0.15

owi

-0.14

 Woods

-0.14

tol

-0.14

 tá»ĵn

-0.14

sei

-0.13

gle

-0.13

é¡¶

-0.13

long

-0.13

POSITIVE LOGITS

berger

0.16

imu

0.15

utenberg

0.15

èŃ

0.15

 Cousins

0.14

lever

0.14

å½

0.14

Î³Ïī

0.13

GraphNode

0.13

chia

0.13

Activations Density 0.041%

references to personal involvement or individual experiences in various contexts

No Comments

No Known Activations