INDEX

Explanations

mentions of the University of California in various contexts

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

Ìģ

-0.16

à¥ĩà¤¯

-0.16

à¤¼à¤¿

-0.15

anko

-0.14

ledi

-0.14

ÅĻÃŃd

-0.14

mutations

-0.14

adero

-0.14

leston

-0.14

ureau

-0.14

POSITIVE LOGITS

ild

0.15

ì°½

0.14

 Barr

0.14

own

0.14

 è¶ħ

0.14

 strictly

0.13

dem

0.13

onal

0.13

 Ø¯Ùĩ

0.13

 Tart

0.13

Activations Density 0.014%

mentions of the University of California in various contexts

No Comments

No Known Activations