INDEX

Explanations

negative evaluations of situations or places

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

_nl

-0.16

ugi

-0.15

idak

-0.15

 POLITICO

-0.14

 Leather

-0.14

Ø¯Ø§Ø±ÛĮ

-0.14

Bid

-0.14

igram

-0.14

 Clay

-0.14

roti

-0.14

POSITIVE LOGITS

ken

0.16

imes

0.15

mit

0.15

kel

0.14

ensitive

0.14

ÐµÑĩ

0.14

cho

0.13

èģ

0.13

has

0.13

Activations Density 0.160%

negative evaluations of situations or places

No Comments

No Known Activations