INDEX

Explanations

terms associated with negative character traits and casual references to people or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onds

-0.15

oni

-0.15

Å¯r

-0.15

StringValue

-0.15

ignet

-0.14

ÙħØ´

-0.14

CSR

-0.14

ãģ£ãģı

-0.14

edList

-0.14

ilk

-0.14

POSITIVE LOGITS

fal

0.15

Ã¡st

0.14

ic

0.14

abler

0.14

.infinity

0.14

oshi

0.14

ëĵ¤

0.14

asal

0.13

iber

0.13

 Jason

0.13

Activations Density 0.407%

terms associated with negative character traits and casual references to people or situations

No Comments

No Known Activations