INDEX

Explanations

references to comments and commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

combe

-0.16

yr

-0.15

ning

-0.15

ouz

-0.15

 ActionTypes

-0.15

uments

-0.15

 concept

-0.15

pel

-0.15

em

-0.14

 commenting

-0.14

POSITIVE LOGITS

aries

0.30

aires

0.25

ary

0.22

ers

0.21

ariat

0.19

ative

0.19

eting

0.18

luv

0.18

ators

0.18

ARY

0.18

Activations Density 0.030%

references to comments and commentary

No Comments

No Known Activations