INDEX

Explanations

phrases expressing reactions or affirmations

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

-0.17

ugi

-0.15

oder

-0.15

ogs

-0.14

 tisk

-0.14

quent

-0.13

 Conway

-0.13

ashtra

-0.13

 pact

-0.13

POSITIVE LOGITS

etten

0.17

enberg

0.17

.mapbox

0.16

ollah

0.15

emin

0.15

ickle

0.15

oho

0.15

InBackground

0.14

lub

0.14

_VERBOSE

0.14

Activations Density 0.017%

phrases expressing reactions or affirmations

No Comments

No Known Activations