INDEX

Explanations

patterns or phrases indicating potential consequences of actions or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

chs

-0.17

amiento

-0.14

è½

-0.14

jar

-0.13

 Keith

-0.13

hin

-0.13

vens

-0.13

 Presence

-0.13

ç§

-0.13

 presence

-0.13

POSITIVE LOGITS

ãĥ¼ãĥį

0.15

ael

0.15

bud

0.14

oe

0.14

AVIS

0.14

antry

0.14

 è±

0.14

imson

0.13

 íļĮ

0.13

fastcall

0.13

Activations Density 0.046%

patterns or phrases indicating potential consequences of actions or trends

No Comments

No Known Activations