INDEX

Explanations

phrases that express the appearance or visual quality of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

info

-0.17

ainless

-0.15

 poison

-0.15

romium

-0.14

 jobs

-0.14

aud

-0.14

ader

-0.14

stal

-0.14

 info

-0.14

 suite

-0.14

POSITIVE LOGITS

 mÅ©i

0.15

azzo

0.15

OKIE

0.14

_REUSE

0.14

 jdbc

0.14

achs

0.14

Ð¾ÑĤÐµ

0.14

linger

0.14

NECT

0.14

.FindGameObjectWithTag

0.14

Activations Density 0.057%

phrases that express the appearance or visual quality of something

No Comments

No Known Activations