INDEX

Explanations

the word "always" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

tfoot

-0.18

oppable

-0.17

Rip

-0.15

ling

-0.15

lings

-0.15

InBackground

-0.14

entes

-0.14

.ft

-0.14

 Fields

-0.14

flo

-0.13

POSITIVE LOGITS

0.17

0.16

imedia

0.15

_argv

0.14

semblies

0.14

Ð¿ÑĢ

0.14

iveau

0.14

0.13

á»Ĳ

0.13

Activations Density 0.020%

the word "always" in various contexts

No Comments

No Known Activations