INDEX

Explanations

keywords related to performance, entertainment, and health

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

OffsetTable

-0.16

íĭ±

-0.15

Ð¾ÐºÐ¾Ð½

-0.14

antine

-0.14

ivec

-0.14

ë¡ľëĤĺ

-0.14

Ø±Ø§Ùģ

-0.13

GenerationStrategy

-0.13

ili

-0.13

lotte

-0.13

POSITIVE LOGITS

lÃŃn

0.15

bin

0.14

redits

0.14

icerca

0.14

 aforementioned

0.14

artment

0.13

caa

0.13

reb

0.13

 cour

0.13

 indeed

0.13

Activations Density 0.101%

keywords related to performance, entertainment, and health

No Comments

No Known Activations