INDEX

Explanations

connections between clauses within sentences, particularly focusing on the usage of "is" and "which" to frame discussions or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ombo

-0.15

-0.14

æĶ¶

-0.14

/antlr

-0.14

ignon

-0.14

sson

-0.14

kul

-0.14

 underside

-0.14

kowski

-0.13

POSITIVE LOGITS

ickle

0.18

weise

0.15

á»Ńa

0.15

ocale

0.14

@class

0.14

OfClass

0.14

 scrim

0.14

yaw

0.14

odes

0.14

ohn

0.14

Activations Density 0.048%

connections between clauses within sentences, particularly focusing on the usage of "is" and "which" to frame discussions or arguments

No Comments

No Known Activations