INDEX

Explanations

adjectives that denote qualities or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

REFERRED

-0.16

.wp

-0.15

alse

-0.14

 Stout

-0.14

amac

-0.14

ittel

-0.14

ruÅ¾

-0.14

ture

-0.13

gang

-0.13

asel

-0.13

POSITIVE LOGITS

ency

0.17

ighthouse

0.16

 Interval

0.16

VRT

0.15

dea

0.14

interval

0.14

 interval

0.14

IDO

0.14

 Rosenstein

0.14

Tro

0.14

Activations Density 0.077%

adjectives that denote qualities or characteristics

No Comments

No Known Activations