INDEX

Explanations

phrases indicating relationships or association between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ryo

-0.16

ONTAL

-0.16

priv

-0.16

byn

-0.15

noop

-0.14

 expiresIn

-0.14

oty

-0.13

 Lá»ĭch

-0.13

á»ĩ

-0.13

isches

-0.13

POSITIVE LOGITS

ctl

0.15

Raised

0.14

izza

0.14

 Raised

0.13

orum

0.13

quine

0.13

ibe

0.13

ater

0.13

kop

0.13

ä¸ĺ

0.12

Activations Density 0.153%

phrases indicating relationships or association between concepts

No Comments

No Known Activations