INDEX

Explanations

arguments related to historical or social injustices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

readcr

-0.16

 portrayed

-0.16

roadcast

-0.15

 denounced

-0.15

@student

-0.15

erves

-0.14

 portray

-0.14

.operations

-0.14

Controls

-0.14

Ð»Ñİ

-0.14

POSITIVE LOGITS

 says

0.61

 states

0.49

 Says

0.44

 notes

0.44

says

0.43

 claims

0.37

states

0.35

 explains

0.35

 recalls

0.35

notes

0.34

Activations Density 0.519%

arguments related to historical or social injustices

No Comments

No Known Activations