INDEX

Explanations

references to government ministries or departments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ab

-0.15

irt

-0.14

enas

-0.14

ger

-0.14

çİ²

-0.14

AMY

-0.14

hem

-0.14

ONT

-0.13

ddy

-0.13

odd

-0.13

POSITIVE LOGITS

marshall

0.17

ÎºÎ±Î½

0.15

umbs

0.15

onen

0.14

rzy

0.14

dens

0.14

flater

0.14

amps

0.13

/trunk

0.13

bens

0.13

Activations Density 0.027%

references to government ministries or departments

No Comments

No Known Activations