INDEX

Explanations

terms related to scientific critique of political practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ierz

-0.18

Tam

-0.15

Tam

-0.15

bin

-0.15

encer

-0.15

iga

-0.15

illes

-0.14

irse

-0.14

undle

-0.14

enge

-0.14

POSITIVE LOGITS

otre

0.15

/drivers

0.15

ecut

0.14

rypton

0.14

SED

0.14

stuff

0.14

ervas

0.14

ONO

0.14

tery

0.14

OG

0.14

Activations Density 0.661%

terms related to scientific critique of political practices

No Comments

No Known Activations