INDEX

Explanations

references to T-shirts, particularly with different styles or designs related to identity and culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

kn

-0.16

ende

-0.15

ining

-0.14

reve

-0.14

Īĺ

-0.14

agini

-0.14

_DUMP

-0.13

thal

-0.13

Sou

-0.13

ne

-0.13

POSITIVE LOGITS

iyat

0.17

ificate

0.15

explode

0.15

leck

0.14

romo

0.14

ikers

0.14

erable

0.14

ÅĽci

0.14

vester

0.14

Activations Density 0.039%

references to T-shirts, particularly with different styles or designs related to identity and culture

No Comments

No Known Activations