INDEX

Explanations

adverbs and adjectives, particularly those describing intensity or manner

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ãĤ·ãĤ§

-0.15

 admittedly

-0.14

fty

-0.14

:///

-0.14

izable

-0.14

 Gust

-0.14

ables

-0.14

tron

-0.14

outs

-0.14

opus

-0.13

POSITIVE LOGITS

 accurate

0.16

etter

0.16

0.15

ono

0.15

omb

0.14

 aware

0.14

etler

0.14

ingly

0.14

ovich

0.14

 Heller

0.14

Activations Density 0.081%

adverbs and adjectives, particularly those describing intensity or manner

No Comments

No Known Activations