INDEX

Explanations

phrases indicating uncertainty or unresolved situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ombo

-0.17

ierge

-0.16

allon

-0.14

ovol

-0.14

kil

-0.13

_INCREMENT

-0.13

INCREMENT

-0.13

lyn

-0.13

bih

-0.13

ello

-0.13

POSITIVE LOGITS

 lasted

0.88

 lasting

0.84

 lasts

0.84

 duration

0.72

dur

0.71

lasting

0.71

-lasting

0.66

 Duration

0.65

duration

0.64

Dur

0.62

Activations Density 0.330%

phrases indicating uncertainty or unresolved situations

No Comments

No Known Activations