INDEX

Explanations

references to television and movie productions

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

antino

-0.20

igham

-0.17

ascar

-0.16

åĪĬ

-0.16

ì»

-0.16

ãĥªãĥ¼

-0.15

áº¯c

-0.15

slideUp

-0.15

ÙĪÙĥ

-0.15

CMP

-0.14

POSITIVE LOGITS

zon

0.17

 fatt

0.15

thon

0.14

inka

0.14

ola

0.14

ipa

0.14

 Ness

0.14

oldem

0.13

Activations Density 0.033%

references to television and movie productions

No Comments

No Known Activations