INDEX

Explanations

references to prison and incarceration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iska

-0.16

aho

-0.16

à¤¾à¤ł

-0.15

Sdk

-0.15

ENSE

-0.15

 disasters

-0.15

bler

-0.14

 parking

-0.14

 Mechan

-0.14

bah

-0.14

POSITIVE LOGITS

 solitary

0.19

 cell

0.19

entine

0.17

 cells

0.17

guards

0.16

 Transfer

0.16

 Cell

0.16

 transfer

0.16

 privileges

0.15

lest

0.15

Activations Density 0.055%

references to prison and incarceration

No Comments

No Known Activations