INDEX

Explanations

discussions around political claims and misinformation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ree

-0.17

lias

-0.16

ouv

-0.16

-0.15

 Otto

-0.14

ittings

-0.14

nier

-0.14

og

-0.14

kin

-0.14

POSITIVE LOGITS

ksam

0.19

atik

0.18

ailability

0.16

ienza

0.15

 å½±

0.15

Wid

0.15

repos

0.15

ometown

0.14

Jad

0.14

_ctxt

0.14

Activations Density 0.278%

discussions around political claims and misinformation

No Comments

No Known Activations