INDEX

Explanations

references to political groups or collectives

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

obby

-0.16

reff

-0.14

asters

-0.14

ACHI

-0.14

amin

-0.14

ifar

-0.14

aju

-0.13

chai

-0.13

pak

-0.13

 unchanged

-0.13

POSITIVE LOGITS

ombine

0.17

ToFit

0.17

ovsky

0.16

ØºØ±

0.15

OfSize

0.15

ropoda

0.15

illin

0.15

insky

0.15

edl

0.15

ä¸

0.15

Activations Density 0.001%

references to political groups or collectives

No Comments

No Known Activations