INDEX

Explanations

references to direct engagement or communication with individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ookie

-0.20

arrass

-0.17

ernal

-0.15

oble

-0.15

lian

-0.14

retty

-0.14

esian

-0.14

ogui

-0.14

reme

-0.14

eners

-0.14

POSITIVE LOGITS

edl

0.17

Hed

0.15

lington

0.14

 priv

0.14

 Reliable

0.14

INY

0.14

Zuk

0.13

_Impl

0.13

 Glover

0.13

Activations Density 0.210%

references to direct engagement or communication with individuals or groups

No Comments

No Known Activations