INDEX

Explanations

punctuated phrases and question marks indicating dialogue or speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

quo

-0.15

ÎĲ

-0.14

UNE

-0.14

ailer

-0.14

urgence

-0.13

seau

-0.13

czy

-0.13

ÑĨÐ¸Ð½

-0.13

ÑĮ

-0.13

-floating

-0.13

POSITIVE LOGITS

dcc

0.15

ause

0.15

RenderTarget

0.14

ddl

0.14

beck

0.14

endir

0.13

Exited

0.13

 Airways

0.13

ToMany

0.13

LOCKS

0.13

Activations Density 0.242%

punctuated phrases and question marks indicating dialogue or speech

No Comments

No Known Activations