INDEX

Explanations

references to claims or allegations within the text

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

 Lamp

-0.18

unte

-0.16

angler

-0.15

eme

-0.15

unta

-0.15

âĶ£

-0.15

duk

-0.15

 Valk

-0.14

.ensure

-0.14

arium

-0.14

POSITIVE LOGITS

 defaultManager

0.18

lesh

0.17

_drvdata

0.15

ãĥ£

0.15

 defaultCenter

0.14

 Garr

0.14

Claims

0.14

entes

0.14

egrator

0.14

 claims

0.14

Activations Density 0.017%

references to claims or allegations within the text

No Comments

No Known Activations