INDEX

Explanations

instances of speculation or uncertainty in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

sville

-0.16

Haz

-0.16

Convention

-0.15

 hazÄ±r

-0.15

luk

-0.15

izza

-0.15

oog

-0.14

readcr

-0.14

cision

-0.14

piler

-0.14

POSITIVE LOGITS

 consider

0.15

Ìģ

0.14

ìľ¨

0.14

 prostÄĽ

0.14

tro

0.14

.Restrict

0.14

umba

0.14

ors

0.14

ika

0.14

atk

0.13

Activations Density 0.028%

instances of speculation or uncertainty in the text

No Comments

No Known Activations