INDEX

Explanations

occurrences of the name "Lind," including variations with suffixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uel

-0.17

ÃŃk

-0.16

quin

-0.16

ivate

-0.16

lop

-0.16

ivas

-0.16

athan

-0.15

agna

-0.15

pine

-0.15

POSITIVE LOGITS

quist

0.21

gren

0.20

ahl

0.18

leyin

0.18

 Lind

0.17

ç¸¾

0.16

sey

0.16

emann

0.16

ungi

0.16

bl

0.15

Activations Density 0.007%

occurrences of the name "Lind," including variations with suffixes

No Comments

No Known Activations