INDEX

Explanations

phrases that discuss various causes and their effects, particularly in a medical or environmental context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

lace

-0.16

ird

-0.15

ãĤ¥

-0.15

ÏħÏĩ

-0.15

ize

-0.15

 increasingly

-0.14

ra

-0.14

ÅĻ

-0.14

row

-0.14

tle

-0.14

POSITIVE LOGITS

anova

0.18

LOPT

0.15

 Tenn

0.15

 cÃ©l

0.15

IGH

0.15

fully

0.14

lessly

0.14

ermo

0.14

ntax

0.14

umer

0.14

Activations Density 0.035%

phrases that discuss various causes and their effects, particularly in a medical or environmental context

No Comments

No Known Activations