INDEX

Explanations

references to prominent figures and dramatic narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

icare

-0.16

éĻ¶

-0.15

SSI

-0.14

Ign

-0.14

iphy

-0.13

_TIMESTAMP

-0.13

Å¡ek

-0.13

mour

-0.13

 kontro

-0.13

HEMA

-0.13

POSITIVE LOGITS

ayout

0.17

.override

0.14

 elemental

0.14

urat

0.14

Nes

0.14

olate

0.13

°

0.13

lox

0.13

 Hogan

0.13

 Hutch

0.13

Activations Density 0.003%

references to prominent figures and dramatic narratives

No Comments

No Known Activations