INDEX

Explanations

references to nations, particularly in the context of government or geopolitical topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Hra

-0.17

ved

-0.16

éŃļ

-0.15

yon

-0.15

 GÃ¼ven

-0.15

aru

-0.14

ivet

-0.14

seg

-0.14

idas

-0.14

çŃĴ

-0.14

POSITIVE LOGITS

enda

0.17

hod

0.15

abox

0.15

anoia

0.14

Fog

0.14

inth

0.14

çĽ

0.14

eyh

0.14

eper

0.14

 diss

0.14

Activations Density 0.003%

references to nations, particularly in the context of government or geopolitical topics

No Comments

No Known Activations