INDEX

Explanations

words related to political discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.ExecuteScalar

-0.16

_latency

-0.15

zeÅĦ

-0.14

ÑĥÑĢÐ½

-0.14

âĶģ

-0.14

sembles

-0.14

vur

-0.14

Ã³rio

-0.14

.ExecuteReader

-0.14

Normalization

-0.14

POSITIVE LOGITS

ate

0.15

cek

0.14

ally

0.14

unny

0.14

hone

0.13

tum

0.13

ude

0.13

xon

0.13

onus

0.13

ially

0.13

Activations Density 0.010%

words related to political discourse

No Comments

No Known Activations