INDEX

Explanations

instances of dialogue and expressions of inquiry or explanation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

olis

-0.15

nga

-0.15

verbatim

-0.13

ild

-0.13

keh

-0.13

Ð½Ð¸Ð½Ð°

-0.12

echo

-0.12

ora

-0.12

è¯Ń

-0.12

POSITIVE LOGITS

 explain

0.74

 explanation

0.73

 explains

0.68

 explaining

0.67

 expl

0.67

 explanations

0.67

 explained

0.66

 Expl

0.64

 Explain

0.62

explain

0.62

Activations Density 0.263%

instances of dialogue and expressions of inquiry or explanation

No Comments

No Known Activations