INDEX

Explanations

instances of the verb "speak" and its variations, indicating discussions or dialogues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ildo

-0.16

readcr

-0.16

zung

-0.15

aki

-0.15

tk

-0.15

ok

-0.14

ierung

-0.14

ecycle

-0.14

roit

-0.14

rien

-0.14

POSITIVE LOGITS

peare

0.16

ake

0.15

æ¬²

0.14

(#)

0.14

ooled

0.14

inded

0.14

erville

0.14

_COMPARE

0.14

olec

0.13

uhn

0.13

Activations Density 0.046%

instances of the verb "speak" and its variations, indicating discussions or dialogues

No Comments

No Known Activations