INDEX

Explanations

phrases involving comparisons or references to specific objects 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ECT

-0.18

ong

-0.15

Ã¨ve

-0.15

ONG

-0.15

Extensions

-0.14

nap

-0.14

apur

-0.14

 Hayward

-0.14

 dimensions

-0.13

Fel

-0.13

POSITIVE LOGITS

ÙĪÙĦÛĮ

0.17

_marshall

0.16

oli

0.16

ifr

0.15

Ð»Ð¾Ð¶

0.15

LocalizedMessage

0.14

esel

0.14

strup

0.14

marshall

0.14

à¸§à¸£à¸£

0.14

Activations Density 0.007%

phrases involving comparisons or references to specific objects and actions

No Comments

No Known Activations