INDEX

Explanations

terms involving "fle" related to various contexts, likely indicating references to specific attributes or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

shore

-0.15

ÑĪÐºÐ°

-0.14

Å¡t

-0.14

.habbo

-0.14

ront

-0.14

neutral

-0.14

ÑĥÑĪ

-0.13

oshi

-0.13

rest

-0.13

whe

-0.13

POSITIVE LOGITS

xt

0.15

itz

0.15

endale

0.15

div

0.15

yled

0.14

Wei

0.14

dou

0.14

yol

0.14

algo

0.14

0.13

Activations Density 0.010%

terms involving "fle" related to various contexts, likely indicating references to specific attributes or characteristics

No Comments

No Known Activations