INDEX

Explanations

negations and expressions of doubt or impossibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ÏħÎ½

-0.15

Ãºi

-0.14

rove

-0.14

asn

-0.14

VERRIDE

-0.14

ICODE

-0.14

anas

-0.14

RG

-0.13

semb

-0.13

POSITIVE LOGITS

ew

0.15

.Msg

0.14

 exclusively

0.14

 Baum

0.14

ervas

0.14

rve

0.13

ÎµÏģ

0.13

 harm

0.13

uk

0.13

 gere

0.13

Activations Density 0.164%

negations and expressions of doubt or impossibility

No Comments

No Known Activations