INDEX

Explanations

expressions indicating desire or expectation for specific outcomes or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ãªu

-0.15

aptive

-0.15

ÏĢÎ¹

-0.14

Lens

-0.14

gfx

-0.14

thumbnails

-0.14

tvb

-0.14

">ÃĹ</

-0.14

ework

-0.13

POSITIVE LOGITS

enci

0.15

rub

0.15

onde

0.14

_MUT

0.14

rub

0.14

Unchecked

0.13

orsk

0.13

 Perr

0.13

DST

0.13

urity

0.13

Activations Density 0.130%

expressions indicating desire or expectation for specific outcomes or results

No Comments

No Known Activations