INDEX

Explanations

references to financial metrics and evaluations related to companies

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

smarty

-0.15

Ã¦kke

-0.15

zcze

-0.14

viso

-0.14

.KeyChar

-0.14

ÏħÎ³

-0.14

ppe

-0.14

-Clause

-0.14

Ã¢b

-0.13

blas

-0.13

POSITIVE LOGITS

ryan

0.14

 Roth

0.14

 Kitt

0.14

 Junk

0.13

iny

0.13

Kit

0.13

 stakes

0.13

kit

0.13

 Hunt

0.13

Activations Density 0.079%

references to financial metrics and evaluations related to companies

No Comments

No Known Activations