INDEX

Explanations

occurrences of the word "post" and related terms that indicate content categorization or tagging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

onica

-0.18

eb

-0.15

stan

-0.15

ache

-0.15

ester

-0.14

ÑģÑĤÐ°Ð²

-0.14

undan

-0.14

pra

-0.14

allee

-0.14

querque

-0.13

POSITIVE LOGITS

Rh

0.15

 Posts

0.15

Rh

0.15

ized

0.15

Å¡t

0.15

Tag

0.14

quarters

0.14

/tag

0.14

/per

0.13

)NULL

0.13

Activations Density 0.023%

occurrences of the word "post" and related terms that indicate content categorization or tagging

No Comments

No Known Activations