INDEX

Explanations

consistent patterns of positive language and expressions of enjoyment or appreciation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Insn

-0.15

ression

-0.15

ckett

-0.15

anse

-0.15

abbo

-0.14

oot

-0.14

ikk

-0.14

cratch

-0.14

reta

-0.14

 Trait

-0.14

POSITIVE LOGITS

rani

0.16

åĬ

0.16

rique

0.15

ople

0.15

indow

0.14

ilion

0.14

ished

0.14

ware

0.13

oped

0.13

 ëĥ

0.13

Activations Density 0.041%

consistent patterns of positive language and expressions of enjoyment or appreciation

No Comments

No Known Activations