INDEX

Explanations

phrases indicating past experiences or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-xl

-0.14

çļ

-0.14

ÐµÑģÑĤÑĮ

-0.14

Î³Î³

-0.14

adas

-0.14

Ð°ÑĤÐºÑĥ

-0.13

 entrev

-0.13

-Men

-0.13

vailability

-0.13

POSITIVE LOGITS

afone

0.17

opher

0.16

okens

0.15

lege

0.15

come

0.14

eria

0.14

 zÃ¡p

0.14

fwd

0.14

äº¬

0.13

 come

0.13

Activations Density 0.030%

phrases indicating past experiences or actions

No Comments

No Known Activations