INDEX

Explanations

mentions of badges 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ableObject

-0.16

umph

-0.14

mens

-0.14

ociety

-0.14

ieder

-0.14

tract

-0.14

áº§y

-0.14

receipt

-0.13

ITERAL

-0.13

iem

-0.13

POSITIVE LOGITS

inese

0.17

antry

0.16

etti

0.15

0.14

ell

0.14

ĥ

0.14

iran

0.14

zan

0.14

enburg

0.14

Activations Density 0.006%

mentions of badges in various contexts

No Comments

No Known Activations