INDEX

Explanations

terms related to providing clarity or understanding on various topics

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

ÙħÙĤ

-0.17

rna

-0.16

irie

-0.15

otate

-0.15

ivery

-0.15

/Runtime

-0.15

apas

-0.15

udit

-0.14

èĢ

-0.14

bject

-0.14

POSITIVE LOGITS

 light

0.51

 Light

0.41

light

0.37

-light

0.35

Light

0.35

 lights

0.33

 LIGHT

0.33

_light

0.30

luz

0.29

 shed

0.29

Activations Density 0.014%

terms related to providing clarity or understanding on various topics

No Comments

No Known Activations