INDEX

Explanations

conditional phrases that pose hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÄĲT

-0.16

mamak

-0.14

Ø§ÙĦÙĩ

-0.14

ØªØ§

-0.14

 flea

-0.14

gfx

-0.14

Ã¸j

-0.14

ÙĬÙĪÙĨ

-0.13

chein

-0.13

strup

-0.13

POSITIVE LOGITS

embros

0.15

 instead

0.14

ÃŃt

0.14

 someone

0.14

igos

0.14

 Skeleton

0.14

tir

0.14

idget

0.13

ermen

0.13

Activations Density 0.026%

conditional phrases that pose hypothetical scenarios

No Comments

No Known Activations