INDEX

Explanations

the word "since" indicating time references or continuity in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Tween

-0.17

 siguiente

-0.15

áºŃu

-0.15

ingt

-0.15

thers

-0.15

nah

-0.15

mtree

-0.14

endas

-0.14

olec

-0.14

 Leban

-0.14

POSITIVE LOGITS

 since

0.18

IPS

0.16

ÙħØ§

0.15

tant

0.15

forth

0.15

ë¶Ģ

0.14

ammers

0.14

Å¼

0.14

 Since

0.14

Since

0.14

Activations Density 0.059%

the word "since" indicating time references or continuity in context

No Comments

No Known Activations