INDEX

Explanations

references to specific individuals who have achieved notable feats or significant events

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

thro

-0.15

ÏĨÎ¿

-0.15

owell

-0.14

dle

-0.14

etas

-0.14

aises

-0.13

cesso

-0.13

enton

-0.13

è©ŀ

-0.13

Ø¹Ø§Ø±

-0.13

POSITIVE LOGITS

ignum

0.16

PropTypes

0.14

PyObject

0.14

PGA

0.14

(::

0.14

çħĻ

0.14

ëįķ

0.13

Attempt

0.13

 Attempt

0.13

çĢ¬

0.13

Activations Density 0.077%

references to specific individuals who have achieved notable feats or significant events

No Comments

No Known Activations