INDEX

Explanations

conditional phrases or scenarios that relate to making decisions and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

riter

-0.17

_kw

-0.15

arro

-0.14

dif

-0.14

.MaxLength

-0.14

QUIRES

-0.14

nant

-0.14

rior

-0.13

Ã¤ren

-0.13

lict

-0.13

POSITIVE LOGITS

/if

0.15

 Gone

0.14

ulk

0.14

UMB

0.13

ispens

0.13

ushima

0.13

 compared

0.13

 such

0.13

aug

0.13

oug

0.13

Activations Density 0.156%

conditional phrases or scenarios that relate to making decisions and actions

No Comments

No Known Activations