INDEX

Explanations

layout specifications or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Evet

-0.15

³

-0.15

LOSS

-0.15

deaux

-0.14

ebek

-0.14

 conv

-0.14

Ð²Ð¸Ñħ

-0.14

á»Ĩ

-0.14

IBUT

-0.14

POSITIVE LOGITS

Ã¥

0.16

iddles

0.15

itol

0.15

_integral

0.15

swer

0.14

Tab

0.14

Minute

0.14

mission

0.14

iple

0.14

uld

0.14

Activations Density 0.000%

layout specifications or instructions

No Comments

No Known Activations