INDEX

Explanations

expressions of surprise or disbelief regarding unexpected outcomes or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

vac

-0.16

 Koch

-0.15

 Ferd

-0.15

onto

-0.15

ura

-0.14

hora

-0.14

ÃºÄįast

-0.14

erli

-0.14

 vacuum

-0.13

okus

-0.13

POSITIVE LOGITS

lingen

0.17

weise

0.15

lined

0.15

wr

0.15

atham

0.15

nee

0.14

onical

0.14

ilen

0.14

emu

0.14

rices

0.13

Activations Density 0.047%

expressions of surprise or disbelief regarding unexpected outcomes or experiences

No Comments

No Known Activations