INDEX

Explanations

occurrences of the term "Miss" followed by names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.17

 Schwartz

-0.16

bine

-0.15

agas

-0.15

glas

-0.15

å¤«

-0.15

ICA

-0.15

lest

-0.14

lag

-0.14

hit

-0.14

POSITIVE LOGITS

ardi

0.15

redient

0.15

issippi

0.15

ByUsername

0.15

esis

0.14

insky

0.14

Ì§

0.14

ori

0.14

aits

0.14

act

0.14

Activations Density 0.009%

occurrences of the term "Miss" followed by names or titles

No Comments

No Known Activations