INDEX

Explanations

names of individuals and places, particularly those associated with legal or organizational contexts

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

urope

-0.17

edo

-0.15

osemite

-0.15

CellValue

-0.14

JV

-0.14

eton

-0.14

lescope

-0.14

phyl

-0.14

 prem

-0.13

|.

-0.13

POSITIVE LOGITS

ory

0.18

erer

0.16

 infer

0.15

faker

0.15

ronic

0.14

(^

0.14

orig

0.14

ase

0.14

ony

0.14

ige

0.14

Activations Density 0.026%

names of individuals and places, particularly those associated with legal or organizational contexts

No Comments

No Known Activations