INDEX

Explanations

mentions of individuals and their statements in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ìī

-0.18

Trivia

-0.16

assis

-0.16

ãĥ¬ãĥ¼

-0.15

enville

-0.15

 baskets

-0.15

 Autonomous

-0.14

uye

-0.14

Ð±Ð¾ÑĤ

-0.14

UpInside

-0.14

POSITIVE LOGITS

swick

0.16

:↵

0.16

 omas

0.15

ØªÙĪÙĨ

0.14

omas

0.14

 Genesis

0.14

Mil

0.14

_AL

0.14

zie

0.14

_CLK

0.14

Activations Density 0.038%

mentions of individuals and their statements in a narrative context

No Comments

No Known Activations