INDEX

Explanations

mentions of sources and information credibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

è¿İ

-0.14

_DECLARE

-0.13

linger

-0.13

opus

-0.13

ampion

-0.13

chas

-0.13

Ð¾Ð¶Ðµ

-0.12

arser

-0.12

Ø§ÙĦÙĩ

-0.12

gaard

-0.12

POSITIVE LOGITS

 sources

0.42

 source

0.34

 anonymous

0.33

 anonymously

0.33

sources

0.32

 insiders

0.32

 knowledgeable

0.32

 familiar

0.32

 Sources

0.32

 confidential

0.32

Activations Density 0.085%

mentions of sources and information credibility

No Comments

No Known Activations