INDEX

Explanations

references to video content and related media

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

ry

-0.18

te

-0.18

ner

-0.18

me

-0.16

ne

-0.16

/vendor

-0.16

mal

-0.16

fs

-0.16

ri

-0.16

POSITIVE LOGITS

conference

0.26

_TS

0.21

/audio

0.20

electric

0.19

 clip

0.18

hoot

0.18

 Clip

0.17

conut

0.17

 surveillance

0.17

ynthesis

0.17

Activations Density 0.032%

references to video content and related media

No Comments

No Known Activations