INDEX

Explanations

phrases related to user interactions and navigation commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

vig

-0.16

ovel

-0.15

éĻ

-0.15

oundary

-0.14

via

-0.14

é©¾

-0.13

via

-0.13

ymph

-0.13

_resize

-0.13

odont

-0.13

POSITIVE LOGITS

ewood

0.17

cona

0.16

aturated

0.16

 Tune

0.15

olar

0.15

tgl

0.15

readcr

0.14

 ä¸

0.14

OLOR

0.14

ToUpdate

0.14

Activations Density 0.093%

phrases related to user interactions and navigation commands

No Comments

No Known Activations