INDEX

Explanations

mentions of the term "Oscar" in relation to awards or recognition in the film industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

endra

-0.18

opard

-0.15

iry

-0.15

opian

-0.14

 Advoc

-0.14

esh

-0.14

OND

-0.14

oph

-0.14

aic

-0.14

POSITIVE LOGITS

uder

0.17

aris

0.15

unken

0.15

åħ¸

0.15

alion

0.14

 Corps

0.14

inge

0.14

rape

0.14

åħ½

0.14

ãģĵãĤĵãģ«ãģ¡ãģ¯

0.14

Activations Density 0.023%

mentions of the term "Oscar" in relation to awards or recognition in the film industry

No Comments

No Known Activations