INDEX

Explanations

references to discussions or topics in a conversational format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

resse

-0.15

PTS

-0.14

ä»¿

-0.14

ri

-0.14

ambi

-0.14

 bust

-0.13

eba

-0.13

-console

-0.13

SCORE

-0.13

boru

-0.13

POSITIVE LOGITS

-motion

0.15

iyan

0.15

izar

0.15

enser

0.14

hend

0.14

ipur

0.14

 baÅŁta

0.14

.Generated

0.14

);$

0.14

atives

0.13

Activations Density 0.006%

references to discussions or topics in a conversational format

No Comments

No Known Activations