INDEX

Explanations

phrases indicating the concept of "thing" or "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

antaged

-0.14

odable

-0.14

rb

-0.14

esel

-0.13

PA

-0.13

áº¯t

-0.13

iber

-0.13

oppable

-0.13

Tul

-0.13

alam

-0.13

POSITIVE LOGITS

LTR

0.15

 Ð²Ð¸Ñģ

0.15

gz

0.15

uft

0.14

rome

0.14

Ð¼ÐµÑĢÐ¸Ðº

0.14

nero

0.14

lemn

0.13

åĳ

0.13

imeType

0.13

Activations Density 0.016%

phrases indicating the concept of "thing" or "of."

No Comments

No Known Activations