INDEX

Explanations

terms related to content and actions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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¸

-0.14

aines

-0.14

nicos

-0.14

.opensource

-0.13

linger

-0.13

esy

-0.13

{!!

-0.13

ìī¬

-0.13

é¾

-0.13

editary

-0.13

POSITIVE LOGITS

èĤ¥

0.14

unt

0.14

 Comet

0.14

acades

0.14

opleft

0.13

addon

0.13

0.12

adt

0.12

à¥Ĥà¤¦

0.12

íģ¼

0.12

Activations Density 0.824%

terms related to content and actions in various contexts

No Comments

No Known Activations