INDEX

Explanations

credibility and trustworthiness of information sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

oller

-0.18

iment

-0.16

(___

-0.15

 Predictor

-0.15

 DÃ¼n

-0.15

 Hosp

-0.14

GROUND

-0.14

atis

-0.14

ÙĨØ¬

-0.13

iments

-0.13

POSITIVE LOGITS

 reliability

0.18

áº¤

0.16

laÄį

0.15

_CLICKED

0.14

.gov

0.14

 sterling

0.14

ivery

0.14

worth

0.14

UPPORTED

0.14

oenix

0.14

Activations Density 0.261%

credibility and trustworthiness of information sources

No Comments

No Known Activations