INDEX

Explanations

conditional phrases indicating hypothetical situations

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

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.17

illo

-0.16

erna

-0.16

isky

-0.15

ernet

-0.15

Ð¾ÑĢÑĸ

-0.14

lien

-0.14

 Carn

-0.14

ÏĥÎ¼

-0.14

à¸Ńà¸ª

-0.14

POSITIVE LOGITS

cation

0.17

IDGET

0.16

lamaz

0.15

>{@

0.14

ãĥ«ãĥķ

0.13

quoi

0.13

Activations Density 0.101%

conditional phrases indicating hypothetical situations

No Comments

No Known Activations