INDEX

Explanations

proper names of individuals or entities relevant to political and environmental contexts

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

ovu

-0.16

iflower

-0.16

Î¹Ïĥ

-0.15

ematic

-0.15

ims

-0.15

.python

-0.15

ADOS

-0.14

ordum

-0.14

bdb

-0.14

idar

-0.14

POSITIVE LOGITS

tm

0.17

oker

0.16

ivic

0.15

aran

0.14

 Mang

0.14

Mol

0.14

gaard

0.14

ti

0.14

 Scho

0.14

dol

0.14

Activations Density 0.041%

proper names of individuals or entities relevant to political and environmental contexts

No Comments

No Known Activations