INDEX

Explanations

references to a specific individual or name

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

ship

-0.15

orean

-0.14

ALA

-0.14

ogonal

-0.14

ucket

-0.14

uro

-0.14

roj

-0.14

ear

-0.14

ID

-0.13

na

-0.13

POSITIVE LOGITS

mes

0.16

isse

0.16

odes

0.16

uda

0.16

Å¡ov

0.16

hit

0.15

MES

0.15

dense

0.15

.Binding

0.14

pend

0.14

Activations Density 0.019%

references to a specific individual or name

No Comments

No Known Activations