INDEX

Explanations

references to physical injuries, hazards, and legal contexts related to accidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 levels

-0.18

_levels

-0.16

ube

-0.16

 aspects

-0.14

rou

-0.14

din

-0.14

 level

-0.14

reste

-0.13

hook

-0.13

POSITIVE LOGITS

YPRE

0.17

Blockly

0.15

-NLS

0.15

 Tent

0.14

 Seks

0.14

_Tis

0.13

 ì¦

0.13

_TAC

0.13

unya

0.13

Activations Density 0.316%

references to physical injuries, hazards, and legal contexts related to accidents

No Comments

No Known Activations