INDEX

Explanations

references to authorities and collectivist expressions of support or opposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

UTE

-0.15

,[],

-0.15

ynos

-0.14

ãĥ«ãĤ¯

-0.14

csr

-0.14

ÃĸL

-0.14

ead

-0.14

(strpos

-0.14

pone

-0.14

POSITIVE LOGITS

 Archive

0.16

oj

0.15

orte

0.15

uels

0.15

izio

0.15

ãĤº

0.14

linger

0.14

reopen

0.14

Miz

0.14

Hel

0.14

Activations Density 0.000%

references to authorities and collectivist expressions of support or opposition

No Comments

No Known Activations