INDEX

Explanations

terms related to attributes or qualities that indicate value or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.15

ingen

-0.15

nge

-0.15

mey

-0.14

iah

-0.14

ust

-0.13

nel

-0.13

ings

-0.13

ar

-0.13

POSITIVE LOGITS

ly

0.19

rieve

0.17

ness

0.16

perl

0.16

âĢĮØªØ±ÛĮÙĨ

0.15

_ARGUMENT

0.14

OID

0.14

rve

0.14

lich

0.14

mente

0.14

Activations Density 0.435%

terms related to attributes or qualities that indicate value or significance

No Comments

No Known Activations