INDEX

Explanations

references to specific racing events and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

bid

-0.15

_PATCH

-0.15

 Kemp

-0.15

ogan

-0.14

bigint

-0.14

ÙĴÙĩ

-0.14

ãĥ¼ãĥ³

-0.14

otti

-0.14

 rigid

-0.14

urrets

-0.14

POSITIVE LOGITS

odel

0.16

_FLAGS

0.14

ubo

0.14

 Childhood

0.14

plural

0.13

ecut

0.13

 Warn

0.13

cak

0.13

uki

0.13

uard

0.13

Activations Density 0.018%

references to specific racing events and locations

No Comments

No Known Activations