INDEX

Explanations

references to sudden increases or spikes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

IRA

-0.15

orraine

-0.15

 persistent

-0.14

Ú¯Ø§ÙĨÛĮ

-0.14

urre

-0.14

haul

-0.14

 Whites

-0.14

ORIZONTAL

-0.14

imers

-0.14

anza

-0.14

POSITIVE LOGITS

fen

0.16

etzt

0.16

0.15

felt

0.15

atal

0.14

SENT

0.14

oppel

0.14

 Sommer

0.13

 Economy

0.13

stry

0.13

Activations Density 0.005%

references to sudden increases or spikes in various contexts

No Comments

No Known Activations