INDEX

Explanations

phrases indicating action or obligation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ELLOW

-0.16

 ÙĨØ³

-0.15

åī²

-0.14

mdp

-0.14

byn

-0.14

ummer

-0.14

aeper

-0.14

 kans

-0.13

nok

-0.13

POSITIVE LOGITS

adies

0.17

FTA

0.15

èĮ

0.15

å¼ĺ

0.14

_handlers

0.14

ubyte

0.14

 Brothers

0.14

 Hung

0.14

LLL

0.14

FETCH

0.14

Activations Density 0.046%

phrases indicating action or obligation

No Comments

No Known Activations