INDEX

Explanations

positive evaluations or affirmations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eya

-0.17

olini

-0.16

,},↵

-0.16

ely

-0.15

pery

-0.15

ãģ¡ãģ¯

-0.14

 brushes

-0.14

eper

-0.14

sig

-0.14

svp

-0.14

POSITIVE LOGITS

ElementsBy

0.15

touches

0.14

PEG

0.14

 Caught

0.14

0.13

usa

0.13

Parcel

0.13

Parcelable

0.13

ousel

0.13

ames

0.13

Activations Density 0.024%

positive evaluations or affirmations within the text

No Comments

No Known Activations