INDEX

Explanations

tentative language and expressions of uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

sonian

-0.17

boa

-0.17

INET

-0.16

 tá»ĳ

-0.15

èĩ´

-0.15

hammer

-0.14

umbn

-0.14

oplevel

-0.14

oyo

-0.14

row

-0.14

POSITIVE LOGITS

 simply

0.16

ixon

0.15

ulling

0.15

 indeed

0.15

ascal

0.14

sek

0.14

orges

0.14

 Hull

0.14

twe

0.14

Activations Density 0.124%

tentative language and expressions of uncertainty

No Comments

No Known Activations